© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84775
    Prev
    Next
    INDEX
    Explanations

    keen interest or desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    饧
    -3.20
    Ꮟ
    -2.73
     immedi
    -2.52
    ⸨
    -2.52
    聍
    -2.47
    怎么可能
    -2.39
    嫺
    -2.38
     termina
    -2.36
     a
    -2.33
     aqueles
    -2.33
    POSITIVE LOGITS
    that
    3.81
    6
    3.31
    7
    3.27
    4
    3.13
    '
    3.02
    8
    2.97
    .
    2.89
    9
    2.80
    鵟
    2.69
    1
    2.67
    Activations Density 0.002%

    No Known Activations